Triple
T1879643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cruquius Pumping Station |
E39822
|
entity |
| Predicate | hasEngineType |
P14429
|
FINISHED |
| Object | Cornish beam engine |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Cornish beam engine | Statement: [Cruquius Pumping Station, hasEngineType, Cornish beam engine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEngineType Context triple: [Cruquius Pumping Station, hasEngineType, Cornish beam engine]
-
A.
testedEngineType
Indicates that an engine of a specified type has been subjected to a test or evaluation.
-
B.
offeredEngineType
Indicates that a particular type of engine is made available or provided as an option in a given context.
-
C.
hasMotivePowerType
chosen
Indicates that an entity (such as a vehicle or machine) operates using a specified type of motive power (e.g., electric, diesel, steam).
-
D.
notableEngineType
Indicates that an entity is particularly recognized for using or being associated with a specific type of engine.
-
E.
hasPlatformType
Indicates that an entity is associated with or characterized by a specific type or category of platform.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a88633e4fc8190b7eb40463e048ec5 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb4f53f408190ae30e1a12721e7d7 |
completed | March 7, 2026, 5:17 a.m. |
| PD | Predicate disambiguation | batch_69abafe497a88190a1da6af2888b71b4 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.